linkfox-echotik-product-video

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted video descriptions and hashtags from TikTok. While a surface for indirect prompt injection exists, it is mitigated by standard agent safety guardrails.
  • Ingestion points: The videoDesc and hashTag fields in the scripts/echotik_list_product_video.py output.
  • Boundary markers: The skill does not currently specify explicit delimiters or isolation instructions for these fields.
  • Capability inventory: The skill possesses network communication capabilities and filesystem access to the local project directory.
  • Sanitization: No specific content-level sanitization is performed on the TikTok video metadata before presentation to the agent.
  • [EXTERNAL_DOWNLOADS]: The scripts/onboarding.py utility relies on external Python packages requests, qrcode, and pillow for account management and payment processing. The documentation explicitly guides the user to install these dependencies via pip.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:11 AM